SOTAVerified

Activity Recognition

Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.

Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 676–700 of 1322 papers

TitleStatusHype
Detector-Free Weakly Supervised Group Activity Recognition—0
Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition—0
Grounding of the Functional Object-Oriented Network in Industrial Tasks—0
SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition—0
VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognition—0
Seeker: Synergizing Mobile and Energy Harvesting Wearable Sensors for Human Activity Recognition—0
EnHDC: Ensemble Learning for Brain-Inspired Hyperdimensional Computing—0
Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition—0
FAR: Fourier Aerial Video RecognitionCode0
Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions—0
Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition—0
Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks—0
Defending Black-box Skeleton-based Human Activity ClassifiersCode0
Human Gaze Guided Attention for Surgical Activity Recognition—0
Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity RecognitionCode0
LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Data—0
MuMu: Cooperative Multitask Learning-based Guided Multimodal Fusion—0
Assessing the State of Self-Supervised Human Activity Recognition using Wearables—0
CROMOSim: A Deep Learning-based Cross-modality Inertial Measurement Simulator—0
Integrated Human Activity Sensing and Communications—0
FLAME: Federated Learning Across Multi-device Environments—0
Multi-View Fusion Transformer for Sensor-Based Human Activity Recognition—0
A Prospective Approach for Human-to-Human Interaction Recognition from Wi-Fi Channel Data using Attention Bidirectional Gated Recurrent Neural Network with GUI Application Implementation—0
Domain Adaptation with Representation Learning and Nonlinear Relation for Time SeriesCode0
Video2IMU: Realistic IMU features and signals from videos—0
Show:102550
← PrevPage 28 of 53Next →
All datasetsRWF-2000Stanford40First-Person Hand Action BenchmarkSelf-stimulatory Behavior Dataset

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Structured Keypoint PoolingAccuracy93.4—Unverified
2Semi-Supervised Hard Attention (SSHA); pretrained on Deepmind Kinetics datasetAccuracy90.4—Unverified
3Human Skeletons + Change DetectionAccuracy90.25—Unverified
4Separable Convolutional LSTMAccuracy89.75—Unverified
5SPIL ConvolutionAccuracy89.3—Unverified
6Flow Gated NetworkAccuracy87.25—Unverified
#ModelMetricClaimedVerifiedStatus
1FocusCLIPTop-3 Accuracy (%)10.47—Unverified
2CLIPTop-3 Accuracy (%)6.49—Unverified
#ModelMetricClaimedVerifiedStatus
1Boutaleb et al.1:1 Accuracy97.91—Unverified
#ModelMetricClaimedVerifiedStatus
1all-landmark-modelActivity Recognition0.76—Unverified